We present Pitarie Touch, a preschooler-friendly picture book recommender system that enables young children to independently explore picture books by expressing their preferences for illustration style and content themes, with minimal robotic guidance. The system was designed to accommodate preschool-aged children’s limited motor and literacy skills through simple touchscreen interactions, allowing preferences to be captured through repeated visual selections rather than text input. The system was deployed in a Japanese public children’s library and made openly available over a period of more than two years. Usage data from 29,741 interactions show that the system was primarily used by preschool-aged children and that a non-trivial subset of users voluntarily returned across multiple months, suggesting sustained engagement that extends beyond purely novelty-driven interaction. These findings provide evidence that a recommender system designed around children’s illustration preferences and supported by developmentally appropriate robotic guidance can sustain voluntary engagement in a real-world library environment. These early-stage results motivate further investigation into children’s stable illustration preferences and their relation to long-term reading behavior in future work.

Location-based games (LBGs) such as Pokémon Go integrate gameplay with real-world locations, creating novel player experiences. Motivated by the idea that new gameplay forms can emerge by rethinking the game field, we have proposed WWW-based games (WBGs) as a new approach to implementing location-based gaming within the WWW. WBGs utilize URLs and web content as game elements, allowing players to interact with web environments in new ways. To explore its feasibility and impact, we developed Text Monster, a game in which players capture monsters inhabiting web pages and compete for control over websites. User studies with two versions of the game demonstrated that WBG is technically feasible and engaging, as players voluntarily participated and exhibited strategic behaviors. Our findings suggest that WBG can influence web usage patterns and introduce new possibilities for interactive web-based experiences.

Lack of labeled data is one of the severest problems facing word sense disambiguation (WSD). We overcome the problem by proposing a method that combines automatic labeled data expansion (Step 1) and semi-supervised learning (Step 2). The Step 1 and 2 methods are both effective, but their combination yields a synergistic effect. In this article, in Step 1, we automatically extract reliable labeled data from raw corpora using dictionary example sentences, even the infrequent and unseen senses (which are not likely to appear in labeled data). Next, in Step 2, we apply a semi-supervised classifier and achieve an improvement using easy-to-get unlabeled data. In this step, we also show that we can guess even unseen senses. We target a SemEval-2010 Japanese WSD task, which is a lexical sample task. Both Step 1 and Step 2 methods performed better than the best published result (76.4 %). Furthermore, the combined method achieved much higher accuracy (84.2 %). In this experiment, up to 50 % of unseen senses are classified correctly. However, the number of unseen senses are small, therefore, we delete one senses per word and apply our proposed method; the results show that the method is effective and robust even for unseen senses.

This article reconsiders the task of MRD-based word sense disambiguation, in extending the basic Lesk algorithm to investigate the impact on WSD performance of different tokenization schemes and methods of definition extension. In experimentation over the Hinoki Sensebank and the Japanese Senseval-2 dictionary task, we demonstrate that sense-sensitive definition extension over hyponyms, hypernyms, and synonyms, combined with definition extension and word tokenization leads to WSD accuracy above both unsupervised and supervised baselines. In doing so, we demonstrate the utility of ontology induction and establish new opportunities for the development of baseline unsupervised WSD methods.

In this paper we describe the current state of a new Japanese lexical resource: the Hinoki treebank. The treebank is built from dictionary definition sentences, and uses an HPSG based Japanese grammar to encode both syntactic and semantic information. It is combined with an ontology based on the definition sentences to give a detailed sense level description of the most familiar 28,000 words of Japanese.

In this paper we present a quantitative and qualitative analysis of annotation in the Hinoki treebank of Japanese, and investigate a method of speeding annotation by using part-of-speech tags. The Hinoki treebank is a Redwoods-style treebank of Japanese dictionary definition sentences. 5,000 sentences are annotated by three different annotators and the agreement evaluated. An average agreement of 65.4% was found using strict agreement, and 83.5% using labeled precision. Exploiting POS tags allowed the annotators to choose the best parse with 19.5% fewer decisions.

Information on subcategorization and selectional restrictions is important for natural language processing tasks such as deep parsing, rule-based machine translation and automatic summarization. In this paper we present a method of adding detailed entries to a bilingual dictionary, based on information in an existing valency dictionary. The method is based on two assumptions: words with similar meaning have similar subcategorization frames and selectional restrictions; and words with the same translations have similar meanings. Based on these assumptions, new valency entries are constructed from words in a plain bilingual dictionary, using entries with similar source-language meaning and the same target-language translations. We evaluate the effects of various measures of similarity in increasing accuracy.